Paraphrase Augmented Task-Oriented Dialog Generation

Abstract

Neural generative models have achieved promising performance on dialog generation tasks if given a huge data set. However, the lack of high-quality dialog data and the expensive data annotation process greatly limit their application in real-world settings. We propose a paraphrase augmented response generation (PARG) framework that jointly trains a paraphrase model and a response generation model to improve the dialog generation performance. We also design a method to automatically construct paraphrase training data set based on dialog state and dialog act labels. PARG is applicable to various dialog generation models, such as TSCP (Lei et al., 2018) and DAMD (Zhang et al., 2019). Experimental results show that the proposed framework improves these state-of-the-art dialog models further on CamRest676 and MultiWOZ. PARG also significantly outperforms other data augmentation methods in dialog generation tasks, especially under low resource settings.

Accepted to ACL 2020, 10 pages, 2 figures

References in corpus (9)

• Adam: A Method for Stochastic Optimization
• Sequence to Sequence Learning with Neural Networks
• mixup: Beyond Empirical Risk Minimization
• Joint Copying and Restricted Generation for Paraphrase
• Sequence-to-Sequence Data Augmentation for Dialogue Language Understanding
• Task-Oriented Dialog Systems that Consider Multiple Appropriate Responses under the Same Context
• Generative Encoder-Decoder Models for Task-Oriented Spoken Dialog Systems with Chatting Capability
• Data Augmentation with Atomic Templates for Spoken Language Understanding
• Dialog State Tracking with Reinforced Data Augmentation

Cited by in corpus (5)

• A Simple Language Model for Task-Oriented Dialogue
• A Probabilistic End-To-End Task-Oriented Dialog Model with Latent Belief States towards Semi-Supervised Learning
• SMRT Chatbots: Improving Non-Task-Oriented Dialog with Simulated Multiple Reference Training
• Nearest Neighbour Few-Shot Learning for Cross-lingual Classification
• Learning from Multiple Noisy Augmented Data Sets for Better Cross-Lingual Spoken Language Understanding